diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 10435b3b9d0f..3be16727f058 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -698,7 +698,8 @@ static void tcp_tsq_handler(struct sock *sk)
 	if ((1 << sk->sk_state) &
 	    (TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | TCPF_CLOSING |
 	     TCPF_CLOSE_WAIT  | TCPF_LAST_ACK))
-		tcp_write_xmit(sk, tcp_current_mss(sk), 0, 0, GFP_ATOMIC);
+		tcp_write_xmit(sk, tcp_current_mss(sk), tcp_sk(sk)->nonagle,
+			       0, GFP_ATOMIC);
 }
 /*
  * One tasklet per cpu tries to send more skbs.
@@ -1904,7 +1905,15 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 
 		if (atomic_read(&sk->sk_wmem_alloc) > limit) {
 			set_bit(TSQ_THROTTLED, &tp->tsq_flags);
-			break;
+			/* It is possible TX completion already happened
+			 * before we set TSQ_THROTTLED, so we must
+			 * test again the condition.
+			 * We abuse smp_mb__after_clear_bit() because
+			 * there is no smp_mb__after_set_bit() yet
+			 */
+			smp_mb__after_clear_bit();
+			if (atomic_read(&sk->sk_wmem_alloc) > limit)
+				break;
 		}
 
 		limit = mss_now;